With the progress of power system

the requirements for grid reliability are increasing.As a key power equipment

the discharge and overheating states of switchgear in operation often trigger multiple types of faults

thus seriously affecting the reliability of power supply.Existing switchgear detection methods mainly focus on the analysis of two-dimensional diagrams

which is difficult to comprehensively reflect the multi-physics field state in three-dimensional space.Therefore

in this study

a multi-physics field coupled finite element model is adopted to explore the temperature and electric field distribution of the switchgear under the operating state.Besides

on the basis of the simulation results combined with the on-site operating state

an agent model of the switchgear based on radial basis function(RBF)neural network is constructed

which can significantly shorten the simulation time.In addition

a switchgear fault diagnosis algorithm based on adaptive neuro-fuzzy inference system(ANFIS)is also studied

and the visual presentation of switchgear state information is realised with the help of Unity

which improves the accuracy and real-time performance of switchgear data monitoring and provides a new way of thinking for preventive operation and maintenance of switchgear.